Textural Feature Based Segmentation: A Repeatable and Accurate Segmentation Approach for Tumors in PET Images

被引:1
|
作者
Pfaehler, Elisabeth [1 ]
Mesotten, Liesbet [2 ,3 ]
Kramer, Gem [4 ]
Thomeer, Michiel [2 ,5 ]
Vanhove, Karolien [2 ,6 ]
de Jong, Johan [1 ]
Adriaensens, Peter [7 ]
Hoekstra, Otto S. [4 ]
Boellaard, Ronald [1 ,4 ]
机构
[1] Univ Groningen, Univ Med Ctr Groningen, Med Imaging Ctr, Dept Nucl Med & Mol Imaging, Groningen, Netherlands
[2] Hassell Univ, Fac Med & Life Sci, Agoralaan Bldg, B-3590 Diepenbeek, Belgium
[3] Ziekenhuis Oost Limburg, Dept Nucl Med, Schiepse Bos 6, B-3600 Genk, Belgium
[4] Vrije Univ Amsterdam Med Ctr, Dept Radiol & Nucl Med, Amsterdam, Netherlands
[5] Ziekenhuis Oost Limburg, Dept Resp Med, Schiepse Bos 6, B-3600 Genk, Belgium
[6] AZ Vesalius Hosp, Dept Resp Med, Hazelereik 51, B-3700 Tongeren, Belgium
[7] Hassell Univ, Inst Mat Res IMO, Div Chem, Agoralaan Bldg D, B-3590 Diepenbeek, Belgium
来源
关键词
Tumor segmentation; PET; Textural feature segmentation; Repeatability; Artificial intelligence; CANCER;
D O I
10.1007/978-3-030-52791-4_1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In oncology, Positron Emission Tomography (PET) is frequently performed for cancer staging and treatment monitoring. Metabolic active tumor volume (MATV) as well as total MATV (TMATV - including primary tumor, lymph nodes and metastasis) derived from PET images have been identified as prognostic factor or for evaluating treatment efficacy in cancer patients. To this end a segmentation approach with high precision and repeatability is important. Moreover, to derive TMATV, a reliable segmentation of the primary tumor as well as all metastasis is essential. However, the implementation of a repeatable and accurate segmentation algorithm remains a challenge. In this work, we propose an artificial intelligence based segmentation method based on textural features (TF) extracted from the PET image. From a large number of textural features, the most important features for the segmentation task were selected. The selected features are used for training a random forest classifier to identify voxels as tumor or background. The algorithm is trained, validated and tested using a lung cancer PET/CT dataset and, additionally, applied on a fully independent test-retest dataset. The approach is especially designed for accurate and repeatable segmentation of primary tumors and metastasis in order to derive TMATV. The segmentation results are compared with conventional segmentation approaches in terms of accuracy and repeatability. In summary, the TF segmentation proposed in this study provided better repeatability and accuracy than conventional segmentation approaches. Moreover, segmentations were accurate for both primary tumors and metastasis and the proposed algorithm is therefore a good candidate for PET tumor segmentation.
引用
收藏
页码:3 / 14
页数:12
相关论文
共 50 条
  • [1] Textural segmentation of SAR images
    Williams, N
    Vaughan, RA
    [J]. PROGRESS IN ENVIRONMENTAL REMOTE SENSING RESEARCH AND APPLICATIONS, 1996, : 181 - 187
  • [2] An estimation-based segmentation method to delineate tumors in PET images.
    Liu, Ziping
    Laforest, Richard
    Moon, Hae Sol
    Mhlanga, Joyce
    Fraum, Tyler
    Itani, Malak
    Mintz, Aaron
    Dehdashti, Farrokh
    Siegel, Barry
    Jha, Abhinav
    [J]. JOURNAL OF NUCLEAR MEDICINE, 2020, 61
  • [3] A GRAPH-BASED APPROACH FOR FEATURE EXTRACTION AND SEGMENTATION OF MULTIMODAL IMAGES
    Iyer, Geoffrey
    Chanussot, Jocelyn
    Bertozzi, Andrea L.
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3320 - 3324
  • [4] A segmentation based on feature for LSCM sequence images
    Gan, Ke
    Xie, Ming
    Luo, Dai-Sheng
    [J]. 2008, Univ. of Electronic Science and Technology of China (37):
  • [5] A Graph-Theoretic Approach for Segmentation of PET Images
    Bagci, Ulas
    Yao, Jianhua
    Caban, Jesus
    Turkbey, Evrim
    Aras, Omer
    Mollura, Daniel J.
    [J]. 2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2011, : 8479 - 8482
  • [6] Cerebral edema segmentation using textural feature
    Chaudhari, Archana
    Kulkarni, Jayant
    [J]. BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2019, 39 (03) : 599 - 612
  • [7] ACCURATE TUMOR SEGMENTATION IN FDG-PET IMAGES WITH GUIDANCE OF COMPLEMENTARY CT IMAGES
    Lian, Chunfeng
    Ruan, Su
    Denoeux, Thierry
    Guo, Yu
    Vera, Pierre
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 4447 - 4451
  • [8] Segmentation of Lung Images Using Textural Features
    Ilyasova, N. Yu
    Shirokanev, A. S.
    Demin, N. S.
    [J]. 2019 4TH INTERNATIONAL CONFERENCE ON COMMUNICATION, IMAGE AND SIGNAL PROCESSING (CCISP 2019), 2020, 1438
  • [9] TEXTURAL SEGMENTATION OF SIDE SCAN SONAR IMAGES
    QUELLEC, B
    JAN, D
    [J]. ONDE ELECTRIQUE, 1992, 72 (02): : 45 - 49
  • [10] Multiphase segmentation for simultaneously homogeneous and textural images
    Duy Hoang Thai
    Mentch, Lucas
    [J]. APPLIED MATHEMATICS AND COMPUTATION, 2018, 335 : 146 - 181